Author(s)

T Rajkumar, C Aragon, J Bardina, R Britten

Abstract

Prediction of aerodynamic coefficients for wind tunnel data using a genetic algorithm optimized neural network T. Rajkurnar1, C. Aragon2, J. Bardina2 & R. Britten3 1SAIC @ NASA Ames Research Center 2 NASA Ames Research Center 3 QSS @. NASA Ames Research Center Abstract A fast, reliable way of predicting aerodynamic coefficients is produced using a neural network optimized by a genetic algorithm. Basic aerodynamic coefficients (e.g. lift, drag, pitching moment) are modelled as functions of angle of attack and Mach number. The neural network is first trained on a relatively rich set of data from wind tunnel tests or numerical simulations to learn an overall model. Most of the aerodynamic parameters can be well-fitted using polynomial functions. A new set of data, which can be relatively sparse, is then supplied to the network to produce a new model consistent with the previous model and the new data. Because the new model interpolates realistically between the sparse test data points, it is suitable for use in piloted simulations. The genetic algorithm is used to choose a neural network architecture to give best results, avoiding over- and under-fitting of the test data. 1 Introduction Wind tunnels use scaled models to characterize aerodynamic coefficients. The wind tunnel data, in original form, are unsuitable for use in piloted simulations because data obtained in different wind tunnels with different scale models of the same vehicle are not always consistent. Also, measurements of the same coefficient from two different wind tunnels are usually taken at dissimilar values of the

Keywords